vduse: implement DMA sync callbacks

Since commit 295525e2 ("virtio_net: merge dma
operations when filling mergeable buffers"), VDUSE device
require support for DMA's .sync_single_for_cpu() operation
as the memory is non-coherent between the device and CPU
because of the use of a bounce buffer.

This patch implements both .sync_single_for_cpu() and
.sync_single_for_device() callbacks, and also skip bounce
buffer copies during DMA map and unmap operations if the
DMA_ATTR_SKIP_CPU_SYNC attribute is set to avoid extra
copies of the same buffer.
Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Message-Id: <20240219170606.587290-1-maxime.coquelin@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

drivers/vdpa/vdpa_user/iova_domain.c

@@ -373,6 +373,26 @@ static void vduse_domain_free_iova(struct iova_domain *iovad,
 	free_iova_fast(iovad, iova >> shift, iova_len);
 }
 
+void vduse_domain_sync_single_for_device(struct vduse_iova_domain *domain,
+				      dma_addr_t dma_addr, size_t size,
+				      enum dma_data_direction dir)
+{
+	read_lock(&domain->bounce_lock);
+	if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)
+		vduse_domain_bounce(domain, dma_addr, size, DMA_TO_DEVICE);
+	read_unlock(&domain->bounce_lock);
+}
+
+void vduse_domain_sync_single_for_cpu(struct vduse_iova_domain *domain,
+				      dma_addr_t dma_addr, size_t size,
+				      enum dma_data_direction dir)
+{
+	read_lock(&domain->bounce_lock);
+	if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)
+		vduse_domain_bounce(domain, dma_addr, size, DMA_FROM_DEVICE);
+	read_unlock(&domain->bounce_lock);
+}
+
 dma_addr_t vduse_domain_map_page(struct vduse_iova_domain *domain,
 				 struct page *page, unsigned long offset,
 				 size_t size, enum dma_data_direction dir,
@@ -393,7 +413,8 @@ dma_addr_t vduse_domain_map_page(struct vduse_iova_domain *domain,
 	if (vduse_domain_map_bounce_page(domain, (u64)iova, (u64)size, pa))
 		goto err_unlock;
 
-	if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
+	    (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL))
 		vduse_domain_bounce(domain, iova, size, DMA_TO_DEVICE);
 
 	read_unlock(&domain->bounce_lock);
@@ -411,9 +432,9 @@ void vduse_domain_unmap_page(struct vduse_iova_domain *domain,
 			     enum dma_data_direction dir, unsigned long attrs)
 {
 	struct iova_domain *iovad = &domain->stream_iovad;
-
 	read_lock(&domain->bounce_lock);
-	if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
+	    (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL))
 		vduse_domain_bounce(domain, dma_addr, size, DMA_FROM_DEVICE);
 
 	vduse_domain_unmap_bounce_page(domain, (u64)dma_addr, (u64)size);

drivers/vdpa/vdpa_user/iova_domain.h

@@ -44,6 +44,14 @@ int vduse_domain_set_map(struct vduse_iova_domain *domain,
 void vduse_domain_clear_map(struct vduse_iova_domain *domain,
 			    struct vhost_iotlb *iotlb);
 
+void vduse_domain_sync_single_for_device(struct vduse_iova_domain *domain,
+				      dma_addr_t dma_addr, size_t size,
+				      enum dma_data_direction dir);
+
+void vduse_domain_sync_single_for_cpu(struct vduse_iova_domain *domain,
+				      dma_addr_t dma_addr, size_t size,
+				      enum dma_data_direction dir);
+
 dma_addr_t vduse_domain_map_page(struct vduse_iova_domain *domain,
 				 struct page *page, unsigned long offset,
 				 size_t size, enum dma_data_direction dir,

drivers/vdpa/vdpa_user/vduse_dev.c

@@ -798,6 +798,26 @@ static const struct vdpa_config_ops vduse_vdpa_config_ops = {
 	.free			= vduse_vdpa_free,
 };
 
+static void vduse_dev_sync_single_for_device(struct device *dev,
+					     dma_addr_t dma_addr, size_t size,
+					     enum dma_data_direction dir)
+{
+	struct vduse_dev *vdev = dev_to_vduse(dev);
+	struct vduse_iova_domain *domain = vdev->domain;
+
+	vduse_domain_sync_single_for_device(domain, dma_addr, size, dir);
+}
+
+static void vduse_dev_sync_single_for_cpu(struct device *dev,
+					     dma_addr_t dma_addr, size_t size,
+					     enum dma_data_direction dir)
+{
+	struct vduse_dev *vdev = dev_to_vduse(dev);
+	struct vduse_iova_domain *domain = vdev->domain;
+
+	vduse_domain_sync_single_for_cpu(domain, dma_addr, size, dir);
+}
+
 static dma_addr_t vduse_dev_map_page(struct device *dev, struct page *page,
 				     unsigned long offset, size_t size,
 				     enum dma_data_direction dir,
@@ -858,6 +878,8 @@ static size_t vduse_dev_max_mapping_size(struct device *dev)
 }
 
 static const struct dma_map_ops vduse_dev_dma_ops = {
+	.sync_single_for_device = vduse_dev_sync_single_for_device,
+	.sync_single_for_cpu = vduse_dev_sync_single_for_cpu,
 	.map_page = vduse_dev_map_page,
 	.unmap_page = vduse_dev_unmap_page,
 	.alloc = vduse_dev_alloc_coherent,